US5745592A - Method for detecting forgery in a traced signature by measuring an amount of jitter - Google Patents

Method for detecting forgery in a traced signature by measuring an amount of jitter Download PDF

Info

Publication number
US5745592A
US5745592A US08508573 US50857395A US5745592A US 5745592 A US5745592 A US 5745592A US 08508573 US08508573 US 08508573 US 50857395 A US50857395 A US 50857395A US 5745592 A US5745592 A US 5745592A
Authority
US
Grant status
Grant
Patent type
Prior art keywords
signature
jitter
curve
valid
samples
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Expired - Lifetime
Application number
US08508573
Inventor
Vishvjit Singh Nalwa
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
AT&T IPM Corp
Lucent Technologies Inc
Original Assignee
Lucent Technologies Inc
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Grant date

Links

Images

Classifications

    • GPHYSICS
    • G07CHECKING-DEVICES
    • G07CTIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
    • G07C9/00Individual entry or exit registers
    • G07C9/00126Access control not involving the use of a pass
    • G07C9/00134Access control not involving the use of a pass in combination with an identity-check
    • G07C9/0015Access control not involving the use of a pass in combination with an identity-check by means of a handwritten signature
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K9/00Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
    • G06K9/00154Reading or verifying signatures; Writer recognition

Abstract

Forgeries are detected by curve fitting the signature in question. The length of the curve fitted signature and the length of the signature in question are compared. If the signature in question is a traced or copied forgery, it will tend to have a significant amount of jitter which results in a significantly longer length than the curved fitted signature.

Description

BACKGROUND OF THE INVENTION

1. Field of the Invention

The present invention relates to signature analysis; more particularly, a signature verification method.

2. Description of the Related Art

In the past, signatures were verified by comparing a signature in question with a collection of samples of a valid signature. After the signature was normalized to a particular scale, the overall shape of the signature was compared with the stored samples or templates. Unfortunately, this type of comparison was susceptible to forgeries made by tracing or copying a valid signature.

SUMMARY OF THE INVENTION

An embodiment of the present invention provides a method for detecting forged signatures that were made by methods such as tracing a valid signature. As a signature is traced, it typically includes jitter. Jitter results from the many small corrections a person makes in the process of tracing a signature. Forgeries are detected by curve fitting the signature in question. The length of the curve fitted signature and the length of the signature in question are compared. If the signature in question is a traced forgery, it will tend to have a significant amount of jitter which results in a significantly longer length than the curve fitted signature.

In another embodiment of the present invention, samples of valid signatures are collected, and the amount of jitter in each valid signature is measured. Then when a signature in question is checked for authenticity, the amount of jitter can be compared with the amount of jitter included in valid signatures. This helps to prevent the rejection of valid signatures produced by people with jittery signatures.

BRIEF DESCRIPTION OF THE DRAWING

FIG. 1 is a block diagram of a system for verifying signatures;

FIG. 2 illustrates a signature to be analyzed;

FIG. 3 illustrates a segment of the signature of FIG. 2; and

FIG. 4 illustrates the signature segment of FIG. 3 after curve fitting.

DETAILED DESCRIPTION OF THE INVENTION

FIG. 1 illustrates a block diagram of a signature verification system. Signature acquisition device 10 provides an electronic representation of an acquired signature to computer 12. Acquisition device 10 may be a device such as a scanner or an electronic writing tablet. Computer 12 compares the electronic representation of the signature in question with templates produced from samples of valid signatures stored in memory 14. The results of the comparison and any instructions to or from a user are communicated by user interface 16. User interface 16 may include common devices such as a mouse, keyboard or touch screen display. In addition to comparing an electronic representation of a signature in question with templates stored in memory 14, computer 12 also performs a jitter measurement on the signature in question for forgery detection. This jitter measurement helps determine whether a forgery is being attempted using a tracing method.

FIG. 2 illustrates a sample of a signature to be analyzed. Square 30 identifies a segment of the signature that will be discussed for illustrative purposes; however, the curve fittings and jitter measurements of the present invention may be carried out on the entire signature. FIG. 3 illustrates the segment of the signature contained within square 30. It should be noted that signature segment 40 is not a smooth curve and comprises variations away from smoothly drawn curves.

FIG. 4 illustrates signature segment 40 and curve 50 fitted to signature segment 40. Curve 50 is fitted to signature segment 40 using standard techniques such as least squares error fitting with B-splines or polygons. Such a technique is discussed "Curve fitting with conic splines", by T. Pavlidis, ACM Trans. Graphics 2, No. 1, 1983, 1-31., New York, N.Y. The signature to be analyzed is composed of samples 60, 62 and 64. The actual length of the signature in question is determined by measuring the distance between each sample and forming a sum of those distances. For example, the distance between samples 64 and 66 is added to the distance between samples 66 and 68 which is added to the distance between samples 68 and 70. This process is continued through the entire signature. This total actual length is then compared to the total length of fitted curve(s) 50. These two lengths may be compared by forming a ratio as illustrated in equation 1. ##EQU1## In equation 1 the jitter is equal to 1 minus the total length of the fitted curve(s) divided by the sum of the lengths or distances between consecutive samples, where lf is the overall length of the fitted curve(s) 50, lp is the length between consecutive samples such as samples 68 and 70, and the sum of such lengths is represented by the term Σlp. It should be noted that the jitter will be greater than or equal to 0 but less then or equal to 1.

A forgery performed by tracing or copying a valid signature will tend to have a large amount of jitter. Jitter results from the forger making minute corrections for deviation from the original signature while the trace or copy is being made. As a result, a forgery performed using tracing or copying tends to have a larger amount of variation or jitter than a valid signature performed using long smooth motions. When the jitter described by equation 1 approaches 0, the signature in question is very smooth and is most likely not a forgery based on a tracing. On the other hand, if the jitter approaches 1, the signature in question comprises a large number of corrections or jitter, which is indicative of a forgery through tracing.

If no samples of an original signature are available, a measure of jitter can be used to determine whether there is a high probability of a forgery through tracing. A threshold such as 0.5 may be used to alert a user to the possibility of a forgery so that that the user may request a second signature to be executed in the user's presence. If samples of valid signatures are available, the sample signatures may be used to determine whether a certain amount of jitter is typically in a valid signature. Jitter measurements, as described above, are performed on valid signatures so that a jitter value is determined with each sample of a valid signature. If only a single valid signature is available, a single jitter value is used to set a threshold for determining authenticity or validity. The threshold may be set in accordance with equation 2, where j is the jitter measurement of the valid signature and T is the threshold.

T=0.5(j+1)                                                 EQ.2

If a large collection of valid signatures are available, a range of acceptable jitter values for valid signatures may be stored in memory. When a signature is examined for authenticity, the jitter measurement of the signature in question is compared to the threshold or jitter measurements associated with valid signatures. If the jitter measurement of the signature under examination exceeds the threshold or lies significantly outside the range of valid signature jitter values, a forgery is declared. An upper and lower threshold may be set to determine if a measurement lies significantly outside the range. The upper threshold may be determined in accordance with equation 2 where j is the largest jitter measurement of the valid signatures. The lower threshold may be set in accordance with equation 3 where j is the smallest jitter measurement of the valid signature.

T=0.5j                                                     EQ.3

Measuring the jitter in valid sample signatures is particularly useful with regard to signatures obtained from elderly people. Many elderly people have a less steady hand and produce signatures with large amounts of jitter. As a result, false alarms or false indications of a forgery can be reduced by comparing the jitter measurement from the signature in question with a range of acceptable jitter values obtained from valid signatures.

Claims (5)

The invention claimed is:
1. A method for detecting forgery in a traced signature by measuring an amount of jitter in the traced signature, comprising the steps of:
taking a plurality of samples of the traced signature;
forming a sum of distances between consecutive samples belonging to the plurality of samples;
fitting a curve to the traced signature;
measuring a length of the curve; and
detecting forgery in the traced signature by comparing the sum of distances to the length of the curve.
2. The method of claim 1, wherein the step of detecting forgery in the traced signature comprises forming a ratio using the sum of distances and the length of the curve.
3. The method of claim 2, wherein the step of detecting forgery in the traced signature comprises comparing the ratio to a threshold.
4. A method for detecting forgery in a traced signature by measuring an amount of jitter in the traced signature, comprising the steps of:
collecting at least one valid signature;
taking a first plurality of samples of the valid signature;
forming a first sum of distances between consecutive samples belonging to the first plurality of samples;
fitting a first curve to the valid signature;
measuring a first length of the first curve;
determining a threshold by forming a first ratio using the first sum of distances and the first length of the first curve;
taking a second plurality of samples of the traced signature;
forming a second sum of distances between consecutive samples belonging to the second plurality of samples;
fitting a second curve to the traced signature;
measuring a second length of the second curve;
forming a second ratio using the second sum of distances and the second length of the second curve; and
detecting forgery in the traced signature by comparing the second ratio and the threshold.
5. A method for detecting forgery in a traced signature by measuring an amount of jitter in the traced signature, comprising the steps of:
collecting a first valid signature;
taking a first plurality of samples of the first valid signature;
forming a first sum of distances between consecutive samples belonging to the
first plurality of samples;
fitting a first curve to the first valid signature;
measuring a first length of the first curve;
determining a first ratio using the first sum of distances and the first length of the first curve;
collecting a second valid signature;
taking a second plurality of samples of the second valid signature;
forming a second sum of distances between samples belonging to the second plurality of samples;
fitting a second curve to the second valid signature;
measuring a second length of the second curve;
determining a second ratio using the second sum of distances and the second length of the second curve;
determining a range of acceptability using the first and second ratios;
taking a third plurality of samples of the traced signature;
forming a third sum of distances between samples belonging to the third plurality of samples;
fitting a third curve to the traced signature;
measuring a third length of the third curve;
forming a third ratio using the third sum of distances and the third length of the third curve; and
detecting forgery in the traced signature by comparing the third ratio and the range of acceptability.
US08508573 1995-07-27 1995-07-27 Method for detecting forgery in a traced signature by measuring an amount of jitter Expired - Lifetime US5745592A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US08508573 US5745592A (en) 1995-07-27 1995-07-27 Method for detecting forgery in a traced signature by measuring an amount of jitter

Applications Claiming Priority (7)

Application Number Priority Date Filing Date Title
US08508573 US5745592A (en) 1995-07-27 1995-07-27 Method for detecting forgery in a traced signature by measuring an amount of jitter
CA 2179551 CA2179551C (en) 1995-07-27 1996-06-20 Method for signature verification
JP18462896A JP3136270B2 (en) 1995-07-27 1996-07-15 Signature authentication method
DE1996625649 DE69625649D1 (en) 1995-07-27 1996-07-17 Procedures for verification of signatures
DE1996625649 DE69625649T2 (en) 1995-07-27 1996-07-17 Procedures for verification of signatures
EP19960305231 EP0756250B1 (en) 1995-07-27 1996-07-17 Method for signature verification
KR19960030598A KR100404489B1 (en) 1995-07-27 1996-07-26 Method for signature verification

Publications (1)

Publication Number Publication Date
US5745592A true US5745592A (en) 1998-04-28

Family

ID=24023255

Family Applications (1)

Application Number Title Priority Date Filing Date
US08508573 Expired - Lifetime US5745592A (en) 1995-07-27 1995-07-27 Method for detecting forgery in a traced signature by measuring an amount of jitter

Country Status (6)

Country Link
US (1) US5745592A (en)
EP (1) EP0756250B1 (en)
JP (1) JP3136270B2 (en)
KR (1) KR100404489B1 (en)
CA (1) CA2179551C (en)
DE (2) DE69625649D1 (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO1999039302A1 (en) * 1998-01-28 1999-08-05 California Institute Of Technology Camera-based handwriting tracking
US20040095384A1 (en) * 2001-12-04 2004-05-20 Applied Neural Computing Ltd. System for and method of web signature recognition system based on object map
US20040218801A1 (en) * 2002-03-15 2004-11-04 Gilles Houle Systems and methods for handwriting analysis in documents
US20110301921A1 (en) * 2010-06-02 2011-12-08 Livermore Software Technology Corporation Curve Matching for Parameter Identification

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7456820B1 (en) 1999-05-25 2008-11-25 Silverbrook Research Pty Ltd Hand drawing capture via interface surface

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0407307A1 (en) * 1989-07-06 1991-01-09 France Telecom Method and systems for signature verification with optimisation of static parameters
US5251265A (en) * 1990-10-27 1993-10-05 International Business Machines Corporation Automatic signature verification
US5537489A (en) * 1992-07-29 1996-07-16 At&T Corp. Method of normalizing handwritten symbols
US5559895A (en) * 1991-11-08 1996-09-24 Cornell Research Foundation, Inc. Adaptive method and system for real time verification of dynamic human signatures
US5559897A (en) * 1994-01-21 1996-09-24 Lucent Technologies Inc. Methods and systems for performing handwriting recognition from raw graphical image data
US5623555A (en) * 1994-04-18 1997-04-22 Lucent Technologies Inc. Method and apparatus for handwriting decompression using estimated timing information

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4286255A (en) * 1979-02-22 1981-08-25 Burroughs Corporation Signature verification method and apparatus

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0407307A1 (en) * 1989-07-06 1991-01-09 France Telecom Method and systems for signature verification with optimisation of static parameters
US5251265A (en) * 1990-10-27 1993-10-05 International Business Machines Corporation Automatic signature verification
US5559895A (en) * 1991-11-08 1996-09-24 Cornell Research Foundation, Inc. Adaptive method and system for real time verification of dynamic human signatures
US5537489A (en) * 1992-07-29 1996-07-16 At&T Corp. Method of normalizing handwritten symbols
US5559897A (en) * 1994-01-21 1996-09-24 Lucent Technologies Inc. Methods and systems for performing handwriting recognition from raw graphical image data
US5623555A (en) * 1994-04-18 1997-04-22 Lucent Technologies Inc. Method and apparatus for handwriting decompression using estimated timing information

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
Achemlal et al, "Dynamic Signature Verification", Security and Protection in Information Systems, Dec. 1986.
Achemlal et al, Dynamic Signature Verification , Security and Protection in Information Systems, Dec. 1986. *
Pavlidis, "Curve Fitting with Conic Splines", ACM Transactions on Graphics, vol. 2, No. 1, Jan. 1983, pp. 1-31.
Pavlidis, Curve Fitting with Conic Splines , ACM Transactions on Graphics, vol. 2, No. 1, Jan. 1983, pp. 1 31. *

Cited By (22)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO1999039302A1 (en) * 1998-01-28 1999-08-05 California Institute Of Technology Camera-based handwriting tracking
US6633671B2 (en) 1998-01-28 2003-10-14 California Institute Of Technology Camera-based handwriting tracking
US20040095384A1 (en) * 2001-12-04 2004-05-20 Applied Neural Computing Ltd. System for and method of web signature recognition system based on object map
US7715600B2 (en) * 2001-12-04 2010-05-11 Applied Neural Technologies Limited System for and method of web signature recognition system based on object map
US7545959B2 (en) 2002-03-15 2009-06-09 Computer Sciences Corporation Systems and methods for handwriting analysis in documents
US20040228513A1 (en) * 2002-03-15 2004-11-18 Gilles Houle Systems and methods for assessing documents using analysis of machine-printed writing and pre-printed information
US20040237047A1 (en) * 2002-03-15 2004-11-25 Gilles Houle Systems and methods for identifying a document with forged information
US20070110314A1 (en) * 2002-03-15 2007-05-17 Gilles Houle Systems and methods of assessing documents using multi-field profile representations
US20070110311A1 (en) * 2002-03-15 2007-05-17 Gilles Houle Systems and methods of assessing documents using multiple profile representations
US20070110313A1 (en) * 2002-03-15 2007-05-17 Gilles Houle Systems and methods of capturing information using association of text representations
US7545982B2 (en) 2002-03-15 2009-06-09 Computer Sciences Corporation Systems and methods of assessing documents using multi-field profile representations
US20040223637A1 (en) * 2002-03-15 2004-11-11 Gilles Houle Systems and methods for assessing a document using cross-correlation analysis
US7555162B2 (en) 2002-03-15 2009-06-30 Computer Sciences Corporation Systems and methods for assessing a document using cross-correlation analysis
US7593575B2 (en) 2002-03-15 2009-09-22 Computer Sciences Corporation Systems and methods of capturing information using association of text representations
US7630552B2 (en) 2002-03-15 2009-12-08 Computer Sciences Corporation Systems and methods of assessing documents using multiple profile representations
US7664304B2 (en) 2002-03-15 2010-02-16 Computer Sciences Corporation Systems and methods for assessing documents using analysis of machine-printed writing and pre-printed information
US7706580B2 (en) * 2002-03-15 2010-04-27 Computer Sciences Corporation Systems and methods for identifying a document with forged information
US20040218801A1 (en) * 2002-03-15 2004-11-04 Gilles Houle Systems and methods for handwriting analysis in documents
US20100303309A1 (en) * 2002-03-15 2010-12-02 Computer Sciences Corporation Systems and methods for identifying a document with forged informaton in non-signature information fields
US8005273B2 (en) 2002-03-15 2011-08-23 Computer Sciences Corporation Systems and methods for identifying a document with forged information in non-signature information fields
US20110301921A1 (en) * 2010-06-02 2011-12-08 Livermore Software Technology Corporation Curve Matching for Parameter Identification
US8521484B2 (en) * 2010-06-02 2013-08-27 Livermore Software Technology Corp. Curve matching for parameter identification

Also Published As

Publication number Publication date Type
CA2179551A1 (en) 1997-01-28 application
JPH0944667A (en) 1997-02-14 application
JP3136270B2 (en) 2001-02-19 grant
KR100404489B1 (en) 2004-03-31 grant
DE69625649T2 (en) 2003-08-21 grant
EP0756250A2 (en) 1997-01-29 application
EP0756250B1 (en) 2003-01-08 grant
EP0756250A3 (en) 1999-03-10 application
DE69625649D1 (en) 2003-02-13 grant
CA2179551C (en) 2000-03-14 grant

Similar Documents

Publication Publication Date Title
Janis The problem of validating content analysis
Walters The psychological inventory of criminal thinking styles: Part I: Reliability and preliminary validity
US6895104B2 (en) Image identification system
Sharpley et al. Preliminary validation of the Abbreviated Spanier Dyadic Adjustment Scale: Some psychometric data regarding a screening test of marital adjustment
Grother et al. Performance of biometric quality measures
Pentland Fractal-based description of natural scenes
US5892838A (en) Biometric recognition using a classification neural network
US6751348B2 (en) Automated detection of pornographic images
De Maesschalck et al. Decision criteria for soft independent modelling of class analogy applied to near infrared data
US5796857A (en) Apparatus for fingerprint verification using different verification method in accordance with quality grade data
Princen et al. A hierarchical approach to line extraction based on the Hough transform
US5450504A (en) Method for finding a most likely matching of a target facial image in a data base of facial images
Candell et al. An iterative procedure for linking metrics and assessing item bias in item response theory
US5257320A (en) Signature verification system
US20010026631A1 (en) Systems and methods for identifying images
US20040136574A1 (en) Face image processing apparatus and method
EP0782090A2 (en) Method and apparatus for parametric signature verification
US20020181749A1 (en) Fingerprint image evaluating method and fingerprint matching device
Chen Sensitivity of goodness of fit indexes to lack of measurement invariance
US6236740B1 (en) Signature verification apparatus and method utilizing relative angle measurements
Rossi et al. Reconstruction from projections based on detection and estimation of objects--Parts I and II: Performance analysis and robustness analysis
Taswell Limiting dilution assays for the determination of immunocompetent cell frequencies. III. Validity tests for the single-hit Poisson model
Fairhurst Signature verification revisited: promoting practical exploitation of biometric technology
US7046829B2 (en) Fingerprint verification
US20040247177A1 (en) Image processing

Legal Events

Date Code Title Description
AS Assignment

Owner name: AT&T IPM CORP., FLORIDA

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:NALWA, VISHVJIT S.;REEL/FRAME:007623/0899

Effective date: 19950727

AS Assignment

Owner name: THE CHASE MANHATTAN BANK, AS COLLATERAL AGENT, TEX

Free format text: CONDITIONAL ASSIGNMENT OF AND SECURITY INTEREST IN PATENT RIGHTS;ASSIGNOR:LUCENT TECHNOLOGIES INC. (DE CORPORATION);REEL/FRAME:011722/0048

Effective date: 20010222

FPAY Fee payment

Year of fee payment: 4

FPAY Fee payment

Year of fee payment: 8

AS Assignment

Owner name: LUCENT TECHNOLOGIES INC., NEW JERSEY

Free format text: TERMINATION AND RELEASE OF SECURITY INTEREST IN PATENT RIGHTS;ASSIGNOR:JPMORGAN CHASE BANK, N.A. (FORMERLY KNOWN AS THE CHASE MANHATTAN BANK), AS ADMINISTRATIVE AGENT;REEL/FRAME:018584/0446

Effective date: 20061130

FPAY Fee payment

Year of fee payment: 12

AS Assignment

Owner name: CREDIT SUISSE AG, NEW YORK

Free format text: SECURITY INTEREST;ASSIGNOR:ALCATEL-LUCENT USA INC.;REEL/FRAME:030510/0627

Effective date: 20130130

AS Assignment

Owner name: ALCATEL-LUCENT USA INC., NEW JERSEY

Free format text: RELEASE BY SECURED PARTY;ASSIGNOR:CREDIT SUISSE AG;REEL/FRAME:033950/0261

Effective date: 20140819